agent-tdd-london-swarm

Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm

1.01x

Quality

Does it follow best practices?

Impact

93%

1.01x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-tdd-london-swarm/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an extremely weak description that fails on every dimension. It provides only an invocation command and a name without explaining what the skill does, when to use it, or any natural trigger terms. It is essentially unusable for skill selection among multiple options.

Suggestions

Add a clear 'what' clause describing the concrete actions, e.g., 'Guides test-driven development using the London school (mockist) approach, creating unit tests with mocks/stubs before implementation code.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about TDD, London school testing, mockist TDD, outside-in testing, or writing tests with mocks and stubs.'

Remove the invocation command from the description (it's operational metadata, not descriptive) and replace with capability-focused language that helps Claude distinguish this skill from other testing or development skills.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It only names an agent and an invocation command, with no indication of what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an invocation command with no explanation of purpose or trigger conditions.	1 / 3
Trigger Term Quality	The only potentially relevant terms are 'tdd' and 'london' which are buried in a hyphenated identifier. There are no natural keywords a user would say like 'test-driven development', 'London school TDD', 'mocking', 'unit tests', etc.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it provides no distinguishing characteristics. Without knowing what the skill does, it cannot be reliably differentiated from any other skill.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is an overly verbose description of London School TDD concepts that Claude already understands, padded with fictional 'swarm coordination' APIs that aren't actionable. The core TDD examples are reasonable but redundant, and the lack of any workflow structure, validation steps, or progressive disclosure makes this a poor skill file. It reads more like a tutorial article than an actionable agent instruction set.

Suggestions

Cut content by 60-70%: Remove explanations of TDD concepts Claude already knows, eliminate redundant code examples that illustrate the same mock verification pattern, and drop the fictional swarm coordination APIs unless they reference real, existing tools.

Add a clear sequential workflow: Define explicit steps like '1. Write failing acceptance test → 2. Identify collaborators → 3. Create mocks → 4. Implement to pass → 5. Verify all mock expectations met → 6. Refactor' with validation checkpoints at each stage.

Replace fictional APIs with real guidance: The swarmCoordinator, createSwarmMock, and SwarmContractMonitor references are not real libraries. Either remove them or replace with actual tool usage (e.g., specific jest configuration, test runner commands).

Add progressive disclosure: Extract detailed examples into separate reference files and keep SKILL.md as a concise overview with links to pattern catalogs or example files.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~200+ lines, with significant redundancy across sections. Many code examples illustrate the same concept (mock verification) repeatedly. The 'Swarm Coordination' sections describe vague, non-existent APIs (swarmCoordinator, SwarmContractMonitor) that add bulk without actionable value. Bullet-point lists like 'Core Responsibilities' restate what the methodology sections already cover.	1 / 3
Actionability	The TypeScript code examples are concrete and mostly executable (jest mock setup, expect calls), which is good. However, the 'swarm coordination' code references fictional APIs (swarmCoordinator.notifyTestStart, createSwarmMock, SwarmContractMonitor) that don't exist and aren't defined anywhere, making those sections non-actionable pseudocode. The core London School TDD examples are usable but standard knowledge Claude already possesses.	2 / 3
Workflow Clarity	Despite describing an 'Outside-In Development Flow', there is no clear sequential workflow with validation checkpoints. The numbered sections (1, 2, 3) under methodology are conceptual categories, not ordered steps. There's no guidance on what to do when tests fail, no feedback loops for error recovery, and no clear process for when/how to proceed between stages of TDD.	1 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files and no bundle files to support it. All content is inline regardless of complexity level. There's no separation between quick-start essentials and advanced patterns, and no navigation structure to help find specific information.	1 / 3
	Total	5 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: 2b9e2de

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.